论文标题
跨域的解释引导培训几乎没有分类
Explanation-Guided Training for Cross-Domain Few-Shot Classification
论文作者
论文摘要
跨域少量分类任务（CD-FSC）结合了少数弹药的分类以及跨数据集代表的域的概括的要求。该设置面临着源自每个类别中有限标记的数据的挑战，此外，还来自训练和测试集之间的领域变化。在本文中，我们为现有FSC模型介绍了一种新颖的培训方法。它利用解释得分，从现有的解释方法应用于FSC模型的预测，该方法计算为模型的中间特征图。首先，我们调整层的相关性传播（LRP）方法来解释FSC模型的预测。其次，我们开发了一种模型不合时宜的解释引导训练策略，该培训策略可以动态地找到并强调对预测很重要的特征。我们的贡献并不是针对一种新颖的解释方法，而是在训练阶段的新应用。我们表明，解释引导的培训有效地改善了模型的概括。我们观察到三种不同的FSC模型的精度提高了：RelationNet，跨注意网络和一个基于图的基于图的基于图形的基于图形的型号：Miniimagenet，Cub，Car，Cars，Plose和Plantae。源代码可从https://github.com/sunjiamei/few-shot-lrp-gueded获得
Cross-domain few-shot classification task (CD-FSC) combines few-shot classification with the requirement to generalize across domains represented by datasets. This setup faces challenges originating from the limited labeled data in each class and, additionally, from the domain shift between training and test sets. In this paper, we introduce a novel training approach for existing FSC models. It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models. Firstly, we tailor the layer-wise relevance propagation (LRP) method to explain the predictions of FSC models. Secondly, we develop a model-agnostic explanation-guided training strategy that dynamically finds and emphasizes the features which are important for the predictions. Our contribution does not target a novel explanation method but lies in a novel application of explanations for the training phase. We show that explanation-guided training effectively improves the model generalization. We observe improved accuracy for three different FSC models: RelationNet, cross attention network, and a graph neural network-based formulation, on five few-shot learning datasets: miniImagenet, CUB, Cars, Places, and Plantae. The source code is available at https://github.com/SunJiamei/few-shot-lrp-guided
